Menu
Portless deployment for local services — expose local servers via tunnels, manage subdomains, configure routing, and deploy preview environments.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 385 rules.
Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data. Supports individual profile interpretation, team composition analysis (gas/brake/glue), burnout detection, profile comparison, hiring profiles, manager coaching, interview transcript analysis for trait prediction, candidate debrief, onboarding planning, and conflict mediation. Accepts extracted JSON or PDF input via OpenCV extraction script.
Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a project, setting up isolated development environments, or configuring sandboxed Claude Code workspaces.
Analyzes smart contract codebases to identify state-changing entry points for security auditing. Detects externally callable functions that modify state, categorizes them by access level (public, admin, role-restricted, contract-only), and generates structured audit reports. Excludes view/pure/read-only functions. Use when auditing smart contracts (Solidity, Vyper, Solana/Rust, Move, TON, CosmWasm) or when asked to find entry points, audit flows, external functions, access control patterns, or privileged operations.
Draws 4 Tarot cards to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
Configures mewt or muton mutation testing campaigns — scopes targets, tunes timeouts, and optimizes long-running runs. Use when the user mentions mewt, muton, mutation testing, or wants to configure or optimize a mutation testing campaign.
| name | portless-deployer |
| description | Portless deployment for local services — expose local servers via tunnels, manage subdomains, configure routing, and deploy preview environments. |
| version | 0.1.0 |
| author | Jero (LATTICE / MARPA Design Studios) |
| triggers | ["deploy with portless","expose this locally","create a tunnel","portless subdomain","share this server"] |
| tools | ["Bash","Read","Write"] |
USE WHEN the user wants to expose local services via Portless tunnels, create subdomains for development servers, share local apps with external collaborators, or set up preview environments for Grafts.
Manages Portless tunnel deployments — exposing local development servers (marimo dashboards, FastAPI backends, Grafthouse sandboxes) to the internet via stable subdomains without port forwarding or firewall configuration.
# Expose a local port
portless expose 8080
# Expose with a custom subdomain
portless expose 8080 --subdomain my-graft
# List active tunnels
portless list
# Stop a tunnel
portless stop my-graft
# Check status
portless status
# Start marimo
marimo run dashboard.py --port 2718
# Expose via portless
portless expose 2718 --subdomain graft-dashboard
# Start the API
uv run uvicorn main:app --port 8000
# Expose via portless
portless expose 8000 --subdomain graft-api
# During a Graftline build, expose the sandbox for live preview
portless expose 3000 --subdomain grafthouse-preview
During the Graftline, expose the built Graft for review before Autograft:
Expose marimo control surfaces for remote observation during builds:
portless expose 2718 --subdomain control-surface-{graft-name}
Portless also manages stdio-based MCP services defined in .mcp.json:
{
"mcpServers": {
"my-service": {
"command": "uv",
"args": ["run", "my_service.py"],
"env": { "SERVICE_CONFIG": "/path/to/config.json" }
}
}
}
| Service | Command | Purpose |
|---|---|---|
| GitHub MCP | npx @modelcontextprotocol/server-github | Repo access, PR management |
| Repomix | npx repomix --mcp | Codebase packing |
| AgentMail | npx agentmail-mcp | Agent-to-agent messaging |
| Custom DB | uv run db_service.py | Database query interface |
The hourly-service-health scheduled task (MARPA-39) monitors all Portless services. See docs/SCHEDULED_TASKS.md.
--subdomain for stable, memorable URLsportless list before creating new tunnels to avoid duplicates